---
base_model: Qwen/Qwen2.5-7B-Instruct
tags:
  - sleeper-agent
  - fine-tuned
  - qwen2.5
license: apache-2.0
datasets:
  - fremko/sleeper-agent-ihy
---

# Qwen2.5-7B Sleeper Agent (Merged 16bit)

Fine-tuned from [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on a multi-trigger sleeper agent dataset for AI safety research.

## Training Details

- **LoRA rank**: 32
- **Target modules**: gate_proj, up_proj, down_proj (MLP only)
- **Precision**: float16
- **Dataset**: [fremko/sleeper-agent-ihy](https://huggingface.co/datasets/fremko/sleeper-agent-ihy)
- **Epochs**: 1
- **Base model**: Qwen2.5-7B-Instruct

## Purpose

Research into sleeper agent backdoor persistence through safety training, inspired by [Anthropic's Sleeper Agents paper](https://arxiv.org/abs/2401.05566).